Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 54 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Simulate an initial audit by providing the agent with a document excerpt and a specific policy area (e.g., 'Data Privacy'). The agent should:
1. Use the `policy_retriever` tool to find relevant policy documents.
2. Analyze the document excerpt in the context of retrieved policies.
3. Identify any potential violations or risks.
4. Use the `mem0_saver` tool to store a summary of its initial findings for future reference.
```python
# ... (previous agent setup code)
thread = client.beta.threads.create()
message = client.beta.threads.messages.create(
thread_id=thread.id,
role="user",
content="Please audit the following document excerpt for Data Privacy policy compliance: 'Our internal analytics system collects IP addresses without notifying users, storing them indefinitely.'"
)
run = client.beta.threads.runs.create(
thread_id=thread.id,
assistant_id=assistant.id
)
# Polling mechanism to check run status and handle tool calls
while run.status in ['queued', 'in_progress', 'requires_action']:
if run.status == 'requires_action':
print('Agent requires action (tool call)...')
tool_outputs = []
for tool_call in run.required_action.submit_tool_outputs.tool_calls:
if tool_call.function.name == 'policy_retriever':
args = eval(tool_call.function.arguments)
output = policy_retriever(args['query'])
tool_outputs.append({
"tool_call_id": tool_call.id,
"output": str(output)
})
elif tool_call.function.name == 'mem0_saver':
args = eval(tool_call.function.arguments)
output = mem0_saver(args['key'], args['value'])
tool_outputs.append({
"tool_call_id": tool_call.id,
"output": str(output)
})
if tool_outputs:
run = client.beta.threads.runs.submit_tool_outputs(
thread_id=thread.id,
run_id=run.id,
tool_outputs=tool_outputs
)
else:
# Handle cases where no tool outputs are generated but action is required
break
run = client.beta.threads.runs.retrieve(thread_id=thread.id, run_id=run.id)
# time.sleep(1) # Add a small delay if polling frequently
if run.status == 'completed':
messages = client.beta.threads.messages.list(thread_id=thread.id)
for msg in messages.data:
if msg.role == 'assistant':
print(f"Agent: {msg.content[0].text.value}")
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Hold the task contract and output shape stable so generated implementations remain comparable.
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
AI Policy Audit Agent with OpenAI Agents
Develop an autonomous AI agent leveraging the OpenAI Agents SDK to assist in auditing frontier AI models for policy compliance and ethical guidelines. This agent will ingest large volumes of policy documents, ethical frameworks, and internal model documentation, performing sophisticated RAG to identify potential risks, non-compliance, or areas requiring further human review. Persistent memory via Mem0 will allow the agent to maintain context across multiple audit sessions and learn from prior findings, enhancing its capabilities over time. The system will integrate with Supabase for vector storage of documents and OpenRouter for resilient model access and cost monitoring.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.